How to roll out Claude Code to your engineering team: a 30-day plan

To roll out Claude Code to a team, run a 2-week pilot with 5-10 engineers. Lock down permissions with a managed settings file, give each repo a short CLAUDE.md, add Claude to code review on GitHub, and measure time to merge, not lines of code. Budget $150-250 per developer a month in usage on top of seats (Anthropic).
Here is the plan we use with client teams, week by week, with the exact files and settings.
  • The plan at a glance
  • Week 1: pick the plan, the pilot group and a baseline
  • Week 1: lock down settings for everyone
  • Week 2: give every repo a CLAUDE.md
  • Week 2: turn repeated work into skills
  • Week 3: put Claude into code review
  • Week 3: automate recurring work with scheduled tasks
  • Week 3: measure what changed
  • Week 4: roll out to everyone, or don't
  • Do it yourself or get help

The plan at a glance

Week
Goal
Done when
1
Buy seats, pick 5-10 pilot engineers, record a baseline, lock down settings
Everyone in the pilot can run Claude Code, and nobody can read .env
2
Teach Claude your codebase
Each pilot repo has a CLAUDE.md under 200 lines and 2-3 shared skills
3
Add AI review and scheduled jobs, turn on metrics
@claude answers in PRs, 1-2 jobs run on a schedule, usage shows in your dashboard
4
Decide and expand
You've compared week 4 to the baseline and made a go or no-go call

Week 1: pick the plan, the pilot group and a baseline

Pick the plan

Plan
Price per seat
Best for
Team, standard seat
$20/month billed annually, $25 monthly
PMs, designers and others who mostly use Claude chat
Team, premium seat
$100/month billed annually, $125 monthly, with 5x the usage of a standard seat
Engineers using Claude Code every day, on teams of 2-150
Enterprise
$20/month billed annually, plus usage at API rates, 20-seat minimum
Teams that need SCIM, audit logs, IP allowlisting or custom data retention
Source: Claude pricing and Anthropic's announcement, checked November 2026. Anthropic's announcement puts Claude Code on premium seats. Team plans mix seat types, so only your engineers need them.
What it really costs. Across enterprise deployments, Anthropic reports an average of $13 per developer per active day and $150-250 per developer per month, with 90% of users under $30 per active day (Claude Code docs). Set spend limits per user from day 1.

Pick the pilot group

5-10 engineers from different teams. Include:
  • 2 people who already use AI tools every day
  • 1 skeptic. If you convince them, you'll convince everyone
  • At least 1 person on your oldest, messiest repo

Record a baseline

Write down these 4 numbers for the last 4 weeks, before anyone starts:
  1. Time to merge: from PR opened to merged
  1. Wait for first review
  1. PRs sent back for changes
  1. Releases per week
You'll need them in week 4. Without a baseline, you'll be judging the rollout on how it feels, and that's unreliable: in a 2025 study, experienced developers were 19% slower with AI tools but believed they were 20% faster (METR). Pulse reads these numbers from GitHub for free: connect a repo read-only and see them in a minute.

Week 1: lock down settings for everyone

Don't let each engineer configure Claude Code their own way. A managed settings file applies to everyone and sits above every project and user setting (docs).
OS
Path
macOS
/Library/Application Support/ClaudeCode/managed-settings.json
Linux and WSL
/etc/claude-code/managed-settings.json
Windows
C:\Program Files\ClaudeCode\managed-settings.json
Push it with your device management tool (Jamf, Intune, Kandji). A good starting point:
JSON

Loading editor...

{
  "permissions": {
    "allow": [
      "Bash(npm run lint)",
      "Bash(npm run test *)"
    ],
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(./secrets/**)"
    ],
    "disableBypassPermissionsMode": "disable"
  }
}
What this does:
  • Allows lint and tests without asking every time, so engineers stop clicking "yes" 40 times an hour
  • Denies reading secrets, even if someone asks Claude to
  • Disables the mode that skips permission prompts entirely
To stop engineers from adding their own allow rules, also set "allowManagedPermissionRulesOnly": true.
Settings apply in this order, highest first: managed, command line, .claude/settings.local.json, .claude/settings.json in the repo, then ~/.claude/settings.json per user. Lists merge across files instead of replacing each other (docs).

Week 2: give every repo a CLAUDE.md

CLAUDE.md is the file Claude reads at the start of every session. It's the difference between an agent that guesses your conventions and one that follows them.
Level
Where
Who it's for
Organization
/Library/Application Support/ClaudeCode/CLAUDE.md (macOS), /etc/claude-code/CLAUDE.md (Linux)
Rules for every repo: security, review, commit style
Project
./CLAUDE.md in the repo, committed
Everyone working on this repo
Local
./CLAUDE.local.md, in .gitignore
One engineer's notes
What to put in the project file, in this order:
  1. How to run things: install, dev server, test, lint, migrations
  1. How the code is organized: where routes, services and tests live
  1. Conventions Claude keeps getting wrong: naming, error handling, which library to use for what
  1. Don'ts: "never edit generated files", "never add a dependency without asking"
Keep it under 200 lines (docs). Move long docs into separate files and import them with @docs/architecture.md.
The fastest way to write it: ask Claude to draft CLAUDE.md from the repo, then cut it in half. Every time Claude makes the same mistake twice in the pilot, add 1 line.

Week 2: turn repeated work into skills

CLAUDE.md tells Claude how your codebase works. Skills tell it how your team does a specific job: release notes, a migration, a PR description, a bug report. Write the job down once, commit it, and every engineer and every Claude session does it the same way.
A skill is a folder with a SKILL.md file. Claude reads only the description of each skill at the start of a session, and loads the full instructions when a task matches. Engineers can also run one directly with /skill-name (docs).

Loading editor...

---
name: release-notes
description: Writes customer-facing release notes from merged pull requests. Use when the user asks for release notes, a changelog or what shipped this week.
allowed-tools: Read Grep
---

1. List the pull requests merged since the last release tag.
2. Group them into New, Improved and Fixed. Skip refactors and chores.
3. Write 1 line per change for customers, not engineers: what they can do now.
4. Add the notes to CHANGELOG.md under today's date and show the diff.
The description does the work. Write it the way an engineer would ask: "Use when the user asks for..." A vague description means Claude never picks the skill up on its own.

Where skills live

Scope
Path
Who gets it
Project
.claude/skills//SKILL.md, committed
Everyone who works in the repo
Personal
~/.claude/skills//SKILL.md
1 engineer, in every project
Plugin
/skills//SKILL.md
Every repo where the plugin is installed
Organization
.claude/skills/ inside the managed settings folder
Every laptop with your managed settings

Which skills to write first

Pick tasks the team does at least weekly and keeps doing slightly differently each time.
Skill
Triggered by
Saves
release-notes
"What shipped this week?"
The Friday hour someone spends reading merged PRs
pr-description
"Open a PR for this"
Reviewers asking "what does this change?"
add-endpoint
"Add an API endpoint for..."
New endpoints that ignore your validation, auth and test conventions
db-migration
"Add a column to..."
Migrations without a rollback or a backfill
bug-triage
"Look into this Sentry error"
Fixes before anyone has reproduced the bug

Share skills across repos

Once 3+ repos need the same skills, package them as a plugin in a private marketplace: a Git repo with a .claude-plugin/marketplace.json file (docs). Then turn the plugin on for every laptop from managed settings, so nobody has to install it by hand (docs):
JSON

Loading editor...

{
  "extraKnownMarketplaces": {
    "acme-tools": {
      "source": { "source": "github", "repo": "acme/claude-tools" },
      "autoUpdate": true
    }
  },
  "enabledPlugins": {
    "team-skills@acme-tools": true
  }
}
Start with 2-3 skills, not 20. Every time an engineer explains the same steps to Claude twice, that's the next skill. Remember that a plugin can run code with the user's permissions, so review plugins like any other dependency.

Week 3: put Claude into code review

Faster coding without faster review just moves the queue. Across 10,000 developers in 1,255 teams, engineers completed twice as many code changes with AI, while company-level delivery stayed flat (Faros AI). Review is where the time goes.
Set it up in 4 steps (docs):
  1. Run /install-github-app in Claude Code. It installs the GitHub App, adds the secret and opens a workflow PR.
  1. For many repos, install the app once at the organization level and store the token as an organization-level Actions secret.
  1. Engineers mention @claude in a PR or issue comment to get a review, a fix or an answer.
  1. Cap cost with --max-turns and a workflow timeout.
Keep a human approval on every merge. Claude's review catches the obvious so your reviewers can spend their 15 minutes on design and risk.

Week 3: automate recurring work with scheduled tasks

Skills make Claude do a job well when someone asks. Scheduled tasks make it do the job when nobody asks: a PR digest every morning, a dependency update every Monday, a docs check every night.
Claude Code has 4 ways to run on a schedule (docs):
Option
Runs on
Start it with
Use it for
/loop
Your laptop, while the session is open
/loop 5m check if the deployment finished
Watching a deploy or a long job. Expires after 7 days
Cloud scheduled tasks
Anthropic's cloud, laptop closed
/schedule daily PR review at 9am
Personal routines: a morning PR review, a weekly backlog cleanup
GitHub Actions on a schedule
GitHub runners
A workflow with on: schedule
Team jobs that belong to the repo, not to a person
Headless claude -p
Any server or CI with cron
claude -p "..." --permission-prompts none
Scripts in your own infrastructure
Cloud scheduled tasks are the easiest to start. Create them with /schedule or at claude.ai/code/routines, and pick a trigger: a schedule, an API call or a GitHub event. Two catches from the docs: they're in research preview, and they belong to 1 person's account. They aren't shared with teammates, and their runs count against that person's usage.
So for anything the team depends on, use a scheduled GitHub Action. It lives in the repo, survives people leaving, and shows up in code review (docs):
YAML

Loading editor...

name: Morning PR digest
on:
  schedule:
    - cron: "0 7 * * 1-5"   # 7:00 UTC, weekdays
jobs:
  digest:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: anthropics/claude-code-action@v1
        with:
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
          prompt: "List open pull requests waiting more than 24 hours for review, with author and size, and summarize what merged yesterday."
          claude_args: "--max-turns 10"
Scheduled workflows run from the default branch only. Cron times are in UTC, for GitHub and for cloud tasks.

5 automations worth setting up first

Automation
Schedule
What it does
PR digest
Weekdays, 9am
Lists PRs stuck in review and what merged yesterday
Alert triage
Every morning
Reads new production errors, groups them and drafts a fix for the top one
Dependency updates
Mondays
Bumps minor versions, runs the tests, opens 1 PR
Docs drift
Nightly
Flags docs and CLAUDE.md lines that no longer match the code
Release notes
Fridays
Runs your release-notes skill and opens a PR with the changelog
Give unattended jobs the same guardrails as people: --max-turns, a workflow timeout, and output as a pull request or a comment, never a direct push to main.

Week 3: measure what changed

Turn on telemetry through the managed settings env block, so engineers can't switch it off per repo (docs):
JSON

Loading editor...

{
  "env": {
    "CLAUDE_CODE_ENABLE_TELEMETRY": "1",
    "OTEL_METRICS_EXPORTER": "otlp"
  }
}
You get sessions, lines changed, commits, pull requests, cost and active time per user in your own observability stack. Prompt text is not logged unless you turn it on.
Then compare 2 kinds of numbers:
Track
Tells you
Watch for
Usage: sessions, cost per user
Who adopted it
Engineers who stopped after week 1: ask why
Delivery: time to merge, review wait, PRs sent back, releases
Whether the team ships faster
More PRs but longer review waits
Lines of code is the number to ignore. It always goes up.

Week 4: roll out to everyone, or don't

Compare week 4 with your baseline and decide:
If
Then
Time to merge is down and PRs sent back are flat or down
Roll out to everyone, with the pilot engineers as champions
More PRs, but review waits went up
Fix review first: smaller PRs, Claude review on every PR, then expand
Pilot engineers stopped using it
Ask them why before buying 50 more seats
The DORA 2025 report found that AI is "an amplifier, magnifying an organization's existing strengths and weaknesses." A team with slow reviews and unclear tasks gets more of both. Fix the process along with the tool.
For the rollout itself:
  • 1-hour pairing session per new engineer with a pilot champion, on a real ticket
  • Weekly 30-minute office hours for the first month
  • 1 shared channel where people post what worked and what Claude got wrong

Common mistakes

Do it yourself or get help

Most teams of 10-50 engineers can follow this plan alone in a month. Get help when you don't have someone who can own it for 4 weeks, or when you need it done faster.
Option
Best for
Do it yourself with this plan and Anthropic's docs
A platform or DevEx lead with time to own it
An Anthropic services partner such as Accenture, Deloitte, PwC or KPMG (Claude Partner Network)
Large enterprises with procurement, compliance and thousands of seats
Paralect, a specialist team
Teams of 3-25 developers who want the setup done in weeks, not quarters
What Paralect's rollout looks like, at fixed prices:
Step
What you get
Price
Time
1. Report and AI review
Time to merge, review wait and rework from GitHub, AI review on up to 3 repos, agent instructions for your main repo
$490
3 days
2. Team rollout
Skills for your 5 most repeated tasks, agent-written tests on every PR, 2 pairing sessions per developer, for up to 10 developers
$2,500
2 weeks
3. Whole process
Agents across planning, review, testing, releases and error fixes, for up to 25 developers
$4,900
4 weeks
Tool seats stay yours. Every step comes with a written scope, and the first step is credited if you go on within 30 days. See the offer, or check your team's numbers for free first.

FAQ

How much does Claude Code cost for a team?
A premium Team seat is $100 a month billed annually ($125 monthly). Anthropic reports usage of $150-250 per developer a month on average across enterprise deployments. Enterprise is $20 per seat a month plus usage at API rates, with a 20-seat minimum.
Do we need the Enterprise plan?
Only if you need SCIM provisioning, audit logs, a compliance API, IP allowlisting or custom data retention. SSO, usage analytics and spend controls are already on the Team plan.
Can Claude Code read our secrets?
Only if you let it. Deny Read(./.env) and your secrets folders in managed settings, and keep production credentials off developer laptops.
Does Claude Code work with GitHub?
Yes. The Claude Code GitHub Action reviews PRs and answers @claude mentions on github.com repositories.
Can Claude Code run tasks on a schedule?
Yes. Use /loop for short checks while a session is open, /schedule for cloud tasks that run with your laptop closed, or a GitHub Actions workflow with a cron schedule for jobs the whole team relies on.
How do we share skills across the team?
Commit them to .claude/skills/ in each repo. For many repos, package them as a plugin in a private marketplace and enable it for everyone from managed settings.
How long does a Claude Code rollout take?
About 4 weeks for a team of 10-50: 2 weeks of pilot, 1 week to measure, 1 week to expand.

Sources

Ship faster than
your competition

Focus on customers and sales while we handle product delivery. Hire a dedicated AI maker or a whole product team.

Launch new products
Fix your delivery
Hit fundraising milestones
[Analytics Chart]
Wireframe v0.1
User
Sarah Chen CEO, Founder
$127k
MRR
2,847
Customers
+23%
Growth
Sales Performance
Latest Deal
Customer
Enterprise plan closed
Acme Corp · $12k/mo
© 2026 Paralect, Inc 651 N Broad St, Suite 206, Middletown, 19709, Delaware, United States